Application of the Self-organizing Mapping and Fuzzy Clustering to Microsatellite Data : How to Detect Genetic Structure in Brown Trout (Salmo trutta) Populations

Artificial Neuronal Networks (ANNs) are now currently used for various purposes, from physical and chemical studies to biological ones. Even if they are less used in ecology and populations genetics, recent studies have shown that they can be very efficient for such problems (Cornuet et al. 1996; Foody 1997; Mastrorillo et al. 1997; Guegan et al. 1998). ANNs have several advantages: they can be applied to various data, from environmental variables to genotypes, and are usually more efficient than classical statistical techniques (FDA, for example; see Cornuet et al. 1996). In order to classify biological objects (individuals or populations, for example) using ANNs, two main types of methods can be applied: supervised and unsupervised learning. Supervised learning can be applied to the classification of individuals of unknown origin among already well-defined groups: This has been successfully applied to genetic data on bees (Conuet et al. 1996, with some phylogenetically well separated lineages), and on trout(Aurelle et al. 1998, but with some less clearly differentiated groups).